Unsupervised Representation Learning with Applications to 3D Genome Organization and Cell-Type-Specific Gene Regulatory Programs

Explore unsupervised representation learning techniques and their applications to understanding 3D genome organization and cell-type-specific gene regulatory programs in this 32-minute conference talk. Discover how computational methods can infer cell type-specific gene regulatory networks from single-cell omics datasets and examine the dynamics of three-dimensional genome organization using multitask matrix factorization approaches. Learn about recent developments and challenges in regulatory and systems genomics, with insights drawn from cutting-edge research on cell lineage analysis, genome structure dynamics, and computational genomics methodologies. Gain understanding of how unsupervised learning frameworks can reveal hidden patterns in complex genomic data and their implications for understanding cellular regulation and genome architecture.